Microcredential Course Overview: Reasoning and Topics of Study
Recently, Machine Learning (ML) approaches to data assimilation and modelling have been very successful in interpreting large amounts of data, such as human behavior prediction, marketing, etc. However, direct applications of machine learning methods without understanding the underlying engineering and physics can be challenging. This happens because, on the one hand, the datasets may be too small for the application of ML methods suitable for large data, while, on the other hand, the reliability of the ML output may not be acceptable for high-responsibility industries such as utilities. To address some of these problems, the Physics Informed Neural Networks (PINNs) have been developed. PINNs incorporate learning on the data as well as matching the differential equations and boundary conditions describing the system. PINNs may be superior to standard ML methods in constructing digital twins of engineering problems and operating on small datasets.
The use of PINNs relies on the knowledge of mathematics, physics, and engineering underlying the particular problem and the understanding of how to implement PINNs successfully. The students will start with the basics of neural networks and develop the knowledge of how to build PINNs for particular applications. PINNs have been successfully used for various scientific and industrial applications, including weather/climate predictions, fluid flow in industrial machinery, renewable energy, geophysics and others.
The emphasis of this course is on the hands-on implementation of PINNs for particular problems of science and engineering and the analysis of advantages and potential difficulties in using PINNs in practice. Examples in the course will include topics from math biology, geophysics, wave propagation and other fields.
About the instructor
Prof. Vakhtang Putkaradze received his PhD at the University of Copenhagen, Denmark, and held faculty positions in New Mexico, Colorado State University, and, most recently, at the University of Alberta, where he was a Centennial Professor between 2012-2019. From 2019 to 2022, he led the science and tech part of the Transformation Team at ATCO Ltd, first as a Senior Director and then as a Vice-President. He is now back to the University of Alberta, where he is currently teaching applications of geometric mechanics to neural networks, in particular, efficient computations of Hamiltonian systems using data-based techniques and PINNs. His main topic of interest is using geometric methods in mechanics and various applications. He has received numerous prizes and awards for research and teaching, including Humboldt Fellowship, Senior JSPS fellowship, CAIMS-Fields industrial math prize and G. I. Zaslavsky prize.
General information:
Zoom link for the class and several Jupyter notebooks will soon be posted in eClass external. If you do not receive any emails about updates on eClass, please log in to eClass external using the link below to access that information. If you have trouble doing that please contact the course assistant (Sofiia Huraka) at email below.
Instructor: Prof. Vakhtang Putkaradze, putkarad-at-ualberta.ca; Course assistant: Sofiia Huraka huraka-at-ualberta.ca
Prerequisites: Basic knowledge of calculus and differential equations, ability to program in Python using Jupyter notebooks
Target audience: Graduate and advanced undergraduate students, postdocs, academic staff, engineers employed by industry
Dates & times: please check the next page titled "Schedule".
Location: Zoom link will be provided in eClass. Please do not share this link as this class will be accessible only to registered students.
Homeworks and exercises: All homework is done using prepared Jupyter notebooks in class or individually. The Jupyter notebooks developed for this course will be provided in eClass. Please familiarize yourself with the basics of Jupyter notebooks.
Hardware requirements: A computer with a good access to the Internet. Your computer does not have to be very powerful, e.g., a regular laptop will do. All computations will be done in the cloud. Platform (PC, Mac, Linux) does not matter since all computations will be done in the cloud.
If you wish, you may install all the relevant software on your computer, to run the software locally. The instructors do not take any responsibility for the hardware and software compatibility and cannot provide any IT support for your installation.
Cost for participation and obtaining regular level (audit) certificates:
Undergraduate & graduate students - $200 CAD;
Postdocs - $500 CAD;
Academic staff - $1000 CAD;
Industry members - $2000 CAD.
50% discount applies to all participants of the course who have affiliation with the University of Aberta.
Developer level certificates
In order to get a developer level certificate, students will be expected to complete several projects in the course and deliver them for grading before deadlines posted. The developer-level certificate will also require an additional payment to be made in the amount of 30% of the regular level (audit) certificate for the corresponding category.
Link to payment page: https://marketplace.ualberta.ca/collections/pinns-microocredential-course-dates-tbd
Registration, Resources and Google Colab:
Registration: All sparticipants are expected to register themselves at the University of Alberta eClass: https://eclass-cpd.srv.4ualberta.ca. Please use the link with "August 2024" stated in its name - this is the right one. You will need an email to register. All resources will be provided within that web site. There are two options to register, depending on whether you have a University of Alberta email, according to the instructions on that web page.
If your email is associated with the University of Alberta, you can just log in the eClass using your credentials. After you log in, please send an email to the course assistant Sofiia Huraka at huraka-at-ualberta.ca so we can add you to the list of participants.
If your email is not associated with the University of Alberta, you will also need a security token (username and password) to reach the account creation page. For the security token, please contact course assistant, Sofiia Huraka at huraka-at-ualberta.ca
Google account and Google Colab: We will be using Google Colaboratory for the class: https://colab.research.google.com
It is highly recommended for you to create a Google account for the access to Google Colab.